© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58682
    Prev
    Next
    INDEX
    Explanations

    apache license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cels
    -0.68
    viewport
    -0.66
    
    -0.64
    viewDid
    -0.64
    knn
    -0.64
    ações
    -0.63
    勃
    -0.63
    縹
    -0.63
     театр
    -0.63
     negotiating
    -0.63
    POSITIVE LOGITS
    pani
    0.71
    Tic
    0.69
     foto
    0.68
     dummies
    0.66
    Tetra
    0.64
    PING
    0.64
     Belle
    0.63
    击
    0.63
    foto
    0.63
    GIN
    0.62
    Activations Density 0.112%

    No Known Activations